The adaptive large language models for vaccine prediction: A novel approach to vaccine demand prediction with engineered deviation prompts

Mingming Chen, Qiangsong Wu, Zilong Wang, Qi Qi, Yi Hu and Tenglong Li

PLOS Digital Health, 2026, vol. 5, issue 3, 1-14

Abstract: Accurate vaccine demand forecasting is crucial for minimizing wastage and ensuring efficient immunization programs. In this study, we introduce an Adaptive Large Language Model for Vaccine Prediction (ALLMVP) that integrates large language model (LLM) architectures with an adaptive value correction mechanism. Using vaccination record data from Xuhui District, Shanghai, China (2014–2022), we conducted a comparative analysis of ALLMVP against seven other models, including standard machine learning methods (logistic regression, random forest, Long Short-Term Memory) and their enhanced versions with the same adaptive value correction mechanism. Our findings indicate that traditional models encountered significant challenges in attaining high predictive accuracy, while frameworks based on LLMs markedly enhanced their forecasting capabilities. Notably, ALLMVP achieved an acceptance ratio of 71.43%, which is considerably superior to that of the other models under consideration. Yearly and cumulative evaluations across seven vaccines from the National Immunization Program demonstrated that ALLMVP consistently delivered more precise estimates, aligning closely with actual vaccine demand even under challenging conditions, such as the post-COVID era. These results highlight the potential of adaptive LLM-driven forecasting tools to fullfill stringent prediction accuracy standards set by governments and to aid in data-informed vaccination strategizing. The AI infrastructure underpinning ALLMVP holds the promise of being generalized and deployed across a range of forecasting applications and at a significantly larger scale.Author summary: Making life-saving vaccines available exactly when and where they are needed is a major challenge for public health. Inaccurate forecasts often lead to wasteful surpluses or dangerous shortages. In this study, we developed a new artificial intelligence tool, called ALLMVP, to bridge this gap. By combining the reasoning power of Large Language Models with a specialized mechanism that learns from past errors, our model predicts vaccine demand with much higher precision than traditional methods. We tested our approach using nearly a decade of vaccination records from Shanghai, China. Even during the unpredictable periods following the COVID-19 pandemic, our AI tool consistently provided estimates that closely matched actual usage, significantly outperforming other forecasting tools. We believe our research offers a practical solution for governments to improve their immunization programs and reduce waste. Beyond vaccines, the framework we built has the potential to be used for forecasting a wide range of medical supplies on a much larger scale, helping healthcare systems achieve balance between supply and demand.

Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001273 (text/html)
https://journals.plos.org/digitalhealth/article/fi ... 01273&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pdig00:0001273

DOI: 10.1371/journal.pdig.0001273

Access Statistics for this article

More articles in PLOS Digital Health from Public Library of Science
Bibliographic data for series maintained by digitalhealth ().